Creep behaviour in rocks is a typical mechanical property that is directly linked to the stability of underground engineering. The deformations and rate of rocks creep are not only influenced by time but also by the loading and unloading history. To more accurately predict creep mechanical behaviour of salt rocks, the rocks hardening is described by introducing a state variable. A new three-dimensional creep constitutive model of salt rocks was established to describe the loading and unloading history effect of the rheological properties. In this paper, salt rocks creep tests under various loading and unloading histories were conducted to investigate how different loading routes affect the creep behaviour of salt rocks. The effects of the model state variables were analysed through different indicators. An example verification was carried out with the results of plastic deformation tests performed at different loading paths. The findings indicated the creep rate of stepped loading and the stepped unloading under the same stress level were significantly affected by the loading history. The proposed constitutive model can accurately fit the creep test curves of different loading paths, indicate that it can provided a prediction of the historical effect of the creep behaviour of salt rocks. Different parameters affect the different phases of the creep curve. The parameter k primarily affects the overall shape of the creep curves. Parameters m and c primarily influence the steady-state creep length and creep rates, excluding the initial cycle.

The size distribution of rock fragments significantly influences subsequent operations in geotechnical and mining engineering projects. Thus, accurate prediction of this distribution according to the relevant blasting design parameters is essential. This study employs artificial intelligence methods to predict the fragmentation of open-pit bench blasting. The study employed a dataset comprising 97 blast fragment samples. Random forest and XGBoost models were utilized as base learners. A prediction model was developed using the stacking integrated strategy to enhance predictive performance. The model’s performance was evaluated using the coefficient of determination (R²), the mean square error (MSE), the root mean square error (RMSE), and the mean absolute error (MAE). The results indicated that the model achieved the highest prediction accuracy, with an R² of 0.943. In the training set, the model achieved MSE, RMSE, and MAE values of 0.00269, 0.05187, and 0.03320, while in the testing set, these values were 0.00197, 0.04435, and 0.03687, respectively. The model was validated using five sets of actual blasting block data from a northeastern mining area, which yielded more accurate prediction results. These findings demonstrate that the stacking strategy effectively enhances the prediction performance of a single model and offers innovative approaches to predicting blasting block size.